Unverified50% confidenceBenchmarkExact time
Burn's backward pass performance is only about 3% of theoretical GPU throughput.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/23/2026
First Seen
Valid until: 12/22/2026
Sources
Related Entities
Related Claims
Unverified在旅行规划任务中，2024年初的模型成功率接近0%，但在工具辅助下GPT-4和Claude 3可以达到90%以上的正确率59% similarUnverifiedThe Anthropic research team noted that models trained with RLHF exhibit a 1%–3% performance regression on certain reasoning benchmarks.58% similarUnverifiedDistilBERT reduces BERT's parameter count by 40% through distillation, increases inference speed by 60%, and incurs only approximately 3% performance loss58% similarUnverifiedQwen3.8 Flash Next has a sparsity rate of approximately 95%, using less than 5% of its parameters per inference.58% similarUnverifiedDistilBERT retains approximately 97% of the original model's performance on the GLUE benchmark, with inference speed improved by approximately 60% and model size reduced by 40%.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/942818API
curl https://kongchang.com/api/v1/knowledge/claims/942818MCP
get_claim(id=942818)